Skip to content

SME2 acceleration for CQ4 matmul, prefill attention, and orthogonal embeddings - #697

Closed
ncylich wants to merge 6 commits into
mainfrom
sme2-cq4-acceleration
Closed

SME2 acceleration for CQ4 matmul, prefill attention, and orthogonal embeddings#697
ncylich wants to merge 6 commits into
mainfrom
sme2-cq4-acceleration

Power/speed frontier: flat 2 SME workers at half the thread budget

db45b6b
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar